{"id":"https://openalex.org/W2963508788","doi":"https://doi.org/10.18653/v1/d17-1126","title":"A Continuously Growing Dataset of Sentential Paraphrases","display_name":"A Continuously Growing Dataset of Sentential Paraphrases","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2963508788","doi":"https://doi.org/10.18653/v1/d17-1126","mag":"2963508788"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d17-1126","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1126","pdf_url":"https://www.aclweb.org/anthology/D17-1126.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D17-1126.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058348064","display_name":"Wuwei Lan","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wuwei Lan","raw_affiliation_strings":["Department of Computer Science and Engineering Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034983605","display_name":"Siyu Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siyu Qiu","raw_affiliation_strings":["Computer and Information Science Department University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer and Information Science Department University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675490","display_name":"Hua He","orcid":"https://orcid.org/0000-0002-6084-1034"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hua He","raw_affiliation_strings":["Department of Computer Science University of Maryland, College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070905937","display_name":"Wei Xu","orcid":"https://orcid.org/0000-0002-7044-3232"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Xu","raw_affiliation_strings":["Department of Computer Science and Engineering Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5058348064"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":11.8633,"has_fulltext":true,"cited_by_count":160,"citation_normalized_percentile":{"value":0.98759256,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1224","last_page":"1234"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/paraphrase","display_name":"Paraphrase","score":0.9915639162063599},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8362971544265747},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7777948379516602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7025375962257385},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6778737306594849},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6684449911117554},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5874201655387878},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5226606726646423},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33734700083732605}],"concepts":[{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.9915639162063599},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8362971544265747},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7777948379516602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7025375962257385},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6778737306594849},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6684449911117554},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5874201655387878},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5226606726646423},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33734700083732605},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d17-1126","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1126","pdf_url":"https://www.aclweb.org/anthology/D17-1126.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d17-1126","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1126","pdf_url":"https://www.aclweb.org/anthology/D17-1126.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963508788.pdf","grobid_xml":"https://content.openalex.org/works/W2963508788.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W131533222","https://openalex.org/W1483236033","https://openalex.org/W1498924130","https://openalex.org/W1503259811","https://openalex.org/W1814992895","https://openalex.org/W1822046502","https://openalex.org/W1965605789","https://openalex.org/W1967579779","https://openalex.org/W1980776243","https://openalex.org/W2008127487","https://openalex.org/W2051593977","https://openalex.org/W2061235289","https://openalex.org/W2099884836","https://openalex.org/W2101105183","https://openalex.org/W2108701407","https://openalex.org/W2116900724","https://openalex.org/W2123402141","https://openalex.org/W2124807415","https://openalex.org/W2126664467","https://openalex.org/W2129468719","https://openalex.org/W2130158090","https://openalex.org/W2131726681","https://openalex.org/W2133458109","https://openalex.org/W2134800885","https://openalex.org/W2135875128","https://openalex.org/W2141766660","https://openalex.org/W2143927888","https://openalex.org/W2147444342","https://openalex.org/W2153702313","https://openalex.org/W2155484602","https://openalex.org/W2157765050","https://openalex.org/W2157835502","https://openalex.org/W2159849140","https://openalex.org/W2164290393","https://openalex.org/W2169813772","https://openalex.org/W2173779128","https://openalex.org/W2185606683","https://openalex.org/W2188036686","https://openalex.org/W2204289728","https://openalex.org/W2250225488","https://openalex.org/W2250293945","https://openalex.org/W2250539671","https://openalex.org/W2250565861","https://openalex.org/W2250818554","https://openalex.org/W2251044566","https://openalex.org/W2251199281","https://openalex.org/W2251295383","https://openalex.org/W2251869843","https://openalex.org/W2251882135","https://openalex.org/W2469060249","https://openalex.org/W2511538013","https://openalex.org/W2561311854","https://openalex.org/W2566302710","https://openalex.org/W2595715041","https://openalex.org/W2953369829","https://openalex.org/W4233787372","https://openalex.org/W4300625795"],"related_works":["https://openalex.org/W191017350","https://openalex.org/W3137243147","https://openalex.org/W4206666510","https://openalex.org/W2018298289","https://openalex.org/W2782520308","https://openalex.org/W3175194702","https://openalex.org/W2251069562","https://openalex.org/W3195775898","https://openalex.org/W4287024084","https://openalex.org/W4321512656"],"abstract_inverted_index":{"A":[0],"major":[1],"challenge":[2],"in":[3,51,67],"paraphrase":[4,64,76,91,125],"research":[5],"is":[6,39],"the":[7,47,52,68,73,85],"lack":[8],"of":[9,36,46,63,80],"parallel":[10],"corpora.":[11],"In":[12,93],"this":[13],"paper,":[14],"we":[15,95],"present":[16,72],"a":[17],"new":[18,101],"method":[19,38],"to":[20,55,78],"collect":[21],"large-scale":[22],"sentential":[23,102],"paraphrases":[24,103],"from":[25],"Twitter":[26],"by":[27],"linking":[28],"tweets":[29],"through":[30,123],"shared":[31],"URLs.":[32],"The":[33],"main":[34],"advantage":[35],"our":[37,129],"its":[40],"simplicity,":[41],"as":[42],"it":[43],"gets":[44],"rid":[45],"classifier":[48],"or":[49],"human":[50],"loop":[53],"needed":[54],"select":[56],"data":[57,132],"before":[58],"annotation":[59],"and":[60,84,107,115,131],"subsequent":[61],"application":[62],"identification":[65],"algorithms":[66],"previous":[69],"work.":[70],"We":[71,127],"largest":[74],"human-labeled":[75],"corpus":[77],"date":[79],"51,524":[81],"sentence":[82],"pairs":[83],"first":[86],"cross-domain":[87],"benchmarking":[88],"for":[89,119],"automatic":[90],"identification.":[92],"addition,":[94],"show":[96],"that":[97],"more":[98],"than":[99],"30,000":[100],"can":[104],"be":[105],"easily":[106],"continuously":[108],"captured":[109],"every":[110],"month":[111],"at":[112],"70%":[113],"precision,":[114],"demonstrate":[116],"their":[117],"utility":[118],"downstream":[120],"NLP":[121],"tasks":[122],"phrasal":[124],"extraction.":[126],"make":[128],"code":[130],"freely":[133],"available.":[134],"1":[135]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":41},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":22},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}